def perform_merging(groups, sim_mad, sim_dip, data):
mask = numpy.where(groups > -1)[0]
clusters = numpy.unique(groups[mask])
dmin = numpy.inf
to_merge = [None, None]
for ic1 in xrange(len(clusters)):
idx1 = numpy.where(groups == clusters[ic1])[0]
sd1 = numpy.take(data, idx1, axis=0)
m1 = numpy.median(sd1, 0)
for ic2 in xrange(ic1 + 1, len(clusters)):
idx2 = numpy.where(groups == clusters[ic2])[0]
sd2 = numpy.take(data, idx2, axis=0)
m2 = numpy.median(sd2, 0)
v_n = (m1 - m2)
pr_1 = numpy.dot(sd1, v_n)
pr_2 = numpy.dot(sd2, v_n)
if sim_dip > 0:
sub_data = numpy.concatenate([pr_1, pr_2])
if len(sub_data) > 10:
dist = dip(sub_data) / dip_threshold(
len(sub_data), sim_dip)
else:
dist = numpy.inf
else:
med1 = numpy.median(pr_1)
med2 = numpy.median(pr_2)
mad1 = numpy.median(numpy.abs(pr_1 - med1))**2
mad2 = numpy.median(numpy.abs(pr_2 - med2))**2
norm = mad1 + mad2
dist = numpy.sqrt((med1 - med2)**2 / norm)
if dist < dmin:
dmin = dist
to_merge = [ic1, ic2]
if sim_dip > 0:
thr = 1
else:
thr = sim_mad / 0.674
if dmin < thr:
groups[numpy.where(
groups == clusters[to_merge[1]])[0]] = clusters[to_merge[0]]
return True, groups
return False, groups
def perform_merging(groups, merging_method, merging_param, data):
mask = numpy.where(groups > -1)[0]
clusters = numpy.unique(groups[mask])
dmin = numpy.inf
to_merge = [None, None]
for ic1 in xrange(len(clusters)):
idx1 = numpy.where(groups == clusters[ic1])[0]
sd1 = numpy.take(data, idx1, axis=0)
if merging_method in ['distance', 'dip', 'folding', 'bhatta']:
m1 = numpy.median(sd1, 0)
for ic2 in xrange(ic1 + 1, len(clusters)):
idx2 = numpy.where(groups == clusters[ic2])[0]
sd2 = numpy.take(data, idx2, axis=0)
if merging_method in ['distance', 'dip', 'folding', 'bhatta']:
m2 = numpy.median(sd2, 0)
v_n = (m1 - m2)
pr_1 = numpy.dot(sd1, v_n)
pr_2 = numpy.dot(sd2, v_n)
if merging_method == 'folding':
sub_data = numpy.concatenate([pr_1, pr_2])
unimodal, p_value, phi, _ = batch_folding_test_with_MPA(
sub_data, True)
if unimodal:
dist = p_value
else:
dist = numpy.inf
elif merging_method == 'nd-folding':
sub_data = numpy.vstack((sd1, sd2))[:, :3]
unimodal, p_value, phi, _ = batch_folding_test_with_MPA(
sub_data, True)
if unimodal:
dist = p_value
else:
dist = numpy.inf
elif merging_method == 'dip':
sub_data = numpy.concatenate([pr_1, pr_2])
if len(sub_data) > 5:
dist = dip(sub_data) / dip_threshold(
len(sub_data), merging_param)
else:
dist = numpy.inf
elif merging_method == 'distance':
med1 = numpy.median(pr_1)
med2 = numpy.median(pr_2)
mad1 = numpy.median(numpy.abs(pr_1 - med1))**2
mad2 = numpy.median(numpy.abs(pr_2 - med2))**2
norm = mad1 + mad2
dist = numpy.sqrt((med1 - med2)**2 / norm)
elif merging_method == 'bhatta':
try:
dist = bhatta_dist(pr_1, pr_2)
except Exception:
dist = numpy.inf
elif merging_method == 'nd-bhatta':
try:
dist = nd_bhatta_dist(sd1.T, sd2.T)
except Exception:
dist = numpy.inf
if dist < dmin:
dmin = dist
to_merge = [ic1, ic2]
if merging_method == 'dip':
thr = 1
elif merging_method in [
'folding', 'nd-folding', 'bhatta', 'nd-bhatta'
]:
thr = merging_param
elif merging_method == 'distance':
thr = merging_param / 0.674
if dmin < thr:
ic1, ic2 = to_merge
c1, c2 = clusters[ic1], clusters[ic2]
selection = numpy.where(groups == c2)[0]
groups[selection] = c1
merge = (c1, c2)
return True, groups, merge, dmin
return False, groups, None, None